STAVAG

Overview

STAVAG is a method that identify directionally variable genes (DVGs) and temporally variable genes (TVGs) from spatial transcriptomics (ST) data. It is a unified gradient-boosting framework that models spatial-temporal information to uncover biological meaningful DVGs and TVGs.

Prerequisites

It is recommended to use a Python version 3.9.

• set up conda environment for STAVAG:

conda create -n STAVAG python==3.9

• activate STAVAG from shell:

conda activate STAVAG

• you can install the important Python packages used to run the model are as follows:

pip install scanpy[leiden]
pip install lightgbm
pip install numpy
pip install matplotlib
pip install scikit-learn
pip install scipy

Tutorials

The following are detailed tutorials. Move STAVAG into the Tutorials folder, and you’ll be able to run all the tutorials. All tutorials were ran on an intel 12600kf cpu and validated on an AMD 3900X cpu.

1. Identify DVGs on 2D cSCC data.

2. Identify DVGs on 3D planarian data.

3. Identify DVGs on 3D cortex data along radial direction.

4. Identify TVGs on mouse myocardial infarction progression data.

5. Identify TVGs on mouse embryonic development data.